Deep Reinforcement and InfoMax Learning
We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving and adapting to new RL problems. To test that hypothesis, we introduce an objective based on Deep InfoMax (DIM) which trains the agent to predict the future by maximizing the mutual information between its internal representation of successive timesteps. We test our approach in several synthetic settings, where it successfully learns representations that are predictive of the future. Finally, we augment C51, a strong RL baseline, with our temporal DIM objective and demonstrate improved performance on a continual learning task and on the recently introduced Procgen environment.
Code (1)
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficient solution to robot learning, as it is u…
Contrastive LearningData AugmentationDecoderModel-based Reinforcement Learning+4QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unkno…
Question AnsweringReading ComprehensionThe Variational InfoMax Learning Objective
Bayesian Inference and Information Bottleneck are the two most popular objectives for neural networks, but they can be optimised only via a variational lower bound: the Variational Information Bottleneck (VIB). In this m…
Bayesian InferenceLearning Diverse Options via InfoMax Termination Critic
We consider the problem of autonomously learning reusable temporally extended actions, or options, in reinforcement learning. While options can speed up transfer learning by serving as reusable building blocks, learning …
Continuous ControlDiversityreinforcement-learningReinforcement Learning (RL)+1ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications. For example, intent classification in dialogue systems. The reason is that the inclusion of unsupporte…
Few-Shot Text Classificationintent-classificationIntent ClassificationOut of Distribution (OOD) Detection+3